气体绝缘电器局部放电联合检测的特征优化与故障诊断技术
|
摘要
气体绝缘组合电器(Gas Insulated Switchgear,简称GIS)因其运行安全、可靠性高、占地面积小及电磁环境友好等突出优点，正逐渐普及于城市供电系统中。然而，GIS设备在生产、运输、装配、运行和维修等过程都会不可避免的产生各种潜伏性绝缘缺陷，当这些绝缘缺陷发展到一定程度，若得不到及时治理，会在运行电压的作用下逐步加剧并最终诱发GIS设备绝缘故障，甚至威胁整个电网的安全。研究发现，因绝缘缺陷导致击穿故障之前，往往会先产生不同形式和程度的局部放电（Partial Discharge，简称PD），而PD形式又与绝缘缺陷类型和故障严重程度有着极为密切的内在联系。因此，通过对GIS内部PD进行科学合理的在线检测，并采用与之相适应的识别方法进行故障诊断，是保障GIS设备安全可靠运行的重要途径。
但是，目前针对GIS PD在线监测的手段比较单一，所得到的反映GIS内部绝缘状态的PD信息也不够全面。鉴于此，本文提出采用脉冲电流法、超高频（UltraHigh Frequency，简称UHF）法和荧光光纤检测法对GIS内部典型绝缘缺陷PD进行联合同步检测，通过得到GIS内部金属突出物、金属污染物、绝缘气隙及自由金属微粒等4种典型绝缘缺陷下的复合PD信息，提取出反映不同绝缘缺陷特征的PD统计特征量，并据此构建出一种适用于GIS设备PD识别的支持向量数据描述（Support Vector Data Description，简称SVDD）故障诊断方法。为此，本文所做的主要研究工作有：
①结合电磁波、天线辐射理论及光电子辐射原理，推导UHF信号能量与视在放电量的平方呈线性相关，荧光光纤信号的一次积分值与视在放电量之间的关联关系。通过实验，对不同气压SF6中UHF信号与视在放电量的关联关系做出修正，研究气压的影响特性及修正公式，并实测检验修正公式的有效性。同时，针对不同尺寸绝缘缺陷对PD光信号能量的影响，研究光信号能量受绝缘缺陷尺寸大小的影响特性与修正公式，并通过电场分析影响机理。实测检验荧光光纤检测法对微小绝缘缺陷引起的PD具有较高的灵敏度。
②结合脉冲电流法、UHF法和荧光光纤法，构建出用于检测GIS内部典型绝缘缺陷PD的联合检测系统。通过大量实验，获取了反映GIS典型绝缘缺陷特征的PD复合信息，构造出各类PD信号的φ-u-n三维谱图及φ-u、φ-n二维谱图，并提取出13个表征4种典型绝缘缺陷产生PD信息的统计特征量。在此基础上，采用核主成分分析方法，提取表征4种典型绝缘缺陷产生PD综合特点的特征子集TKPCA，并借鉴最大相关最小冗余算法对原始统计特征进行择优降维，结合能够表征PD源特征的视在放电量q、UHF信号能量E以及荧光光纤信号一次积分A，共同构造出辨识4种典型绝缘缺陷的最优特征子集TBEST。研究表明，该方法不仅有效保留了每类PD信号的特征，同时还显著降低了特征信息的冗余度。
③在PD类型识别中，引入SVDD方法，并借鉴支持向量机(support vectormachine，简SVM)最大化“间隔”思想，提出一种优化半径的OR-SVDD(OptimalRadius SVDD，简称OR-SVDD)方法来解决SVM辨识PD类型存在的漏分或错分问题，弥补了SVDD分类裕度不足的缺点，实现了多类缺陷的有效分类。
④针对SVM和SVDD算法中核函数参数σ与惩罚因子C的选择存在盲目性的问题，结合局部遗传算法和模拟退火算法对SVDD分类器中的核函数参数σ和惩罚因子C进行优化，解决了以往依靠经验设定参数的问题，使σ与C这两个对分类性能影响最大的参数的设置具有科学依据，并提升了算法分类性能和识别效率。
⑤针对实际故障诊断中存在的预定义故障重叠问题，使用主成分分析方法来优化Fisher判别分析（Fisher Discriminant Analysis，简称FDA），结合前文所构建的SVDD故障识别方法，提出一种使重叠的两类预定义故障在原始空间尽量分离后，再在Fisher投影空间实现最大分离的PF-SVDD方法。研究表明：该方法可将存在故障重叠情况时的60%低识别率提高到接近80%，显著增加了该诊断方法实用性。
Gas Insulated Substation (GIS) is widely used in urban power substation becauseof its advantages of small area coverage, operational reliability and low electromagneticpollution. However, due to some reasons in structure and transportation, there areinevitable insulation defects which may cause partial discharge in regular operation.The safe operation of grid is threatened seriously by insulation damage. Therefore, theon-line monitoring and fault type recognition in GIS has been the focus of research inthis field.
In this paper, statistical characteristics of different insulation defects PD signals arestudied based on analyzing researches about PD type recognition home and abroad.Methods to obtain different characteristic parameters are developed from differentangles of partial discharge pattern, Support Vector Data Description method is presentedfor PD type recognition in GIS. The main work and achievements are as follows.
①Large data of discharge experiment in different intensity is acquired by PDUHF monitoring system which has been developed for the detection of four kinds oftypical insulation defects model in the laboratory. The φ-u-n3D PD image and thecorresponding φ-u, φ-n two-dimensional image has been constructed.The results showthat: the differences of four PD image shape are rather obvious, the same type of PDimage shape remains unchanged in different voltage levels. Obtaining the13statisticalfeatures based on the two-dimensional image can lay a foundation for the research ofPD type recognition.
②Based on the electromagnetic theory, antenna and photoelectron radiationtheory, the relationship between apparent discharge quantity calculated by IEC60270and the detection signal could be obtained. Linear relationship between energy of UHFsignal and square of apparent discharge quantity has been found, while linearrelationship between the integral value of the signal of the optical method and thecharge quantity comes out. According to the practical situation, the correction formulaof gas pressure has been get by the research on the influence of different gas pressure toUHF signal and apparent discharge quantity. The effectiveness of optical method hasbeen also proved by experiment result.
③The KPCA method is presented for the extraction of feature subset of fourkinds of insulation defects discharge comprehensive characteristic. The Maximal Relevance Minimal Redundancy method is put forward for dimension reduction of theoriginal statistical characteristics. With apparent discharge quantity q, energy of UHFsignal E and optical energy A, two algorithms are combined to construct optimal featuresubset TBESTto identify four kinds of defects, which effectively retained thecharacteristics of each class of the PD signal and reduced the redundancy of statisticalcharacteristics.
④SVDD is introduced into PD type recognition, based on the principle ofMaximum interval of support vector machine and one to multiple of multipleclassification method, an optimal radius support vector data description algorithm(OR-SVDD) is proposed to solve the disadvantages of missing and wrong classificationin SVM and the lack of classification margin small in SVDD. The principle of“one-to-many” is adopted to solve the difficult problem of multi-class defectclassification, and to improve the identification ability and application value.
⑤As a result of optimization of classification performance, local GA algorithmand SA algorithm have been applied to optimize the kernel parameter σ and the penaltyfactor C of SVDD classifier. According to the real project, PCA-FDA has been proposed.Two overlapping classes of fault would desperate in original space, and then reach themaximum level in Fisher projection space. With the method, the low recognition ratio60%would rise high to80%to improve the applying value.
但是，目前针对GIS PD在线监测的手段比较单一，所得到的反映GIS内部绝缘状态的PD信息也不够全面。鉴于此，本文提出采用脉冲电流法、超高频（UltraHigh Frequency，简称UHF）法和荧光光纤检测法对GIS内部典型绝缘缺陷PD进行联合同步检测，通过得到GIS内部金属突出物、金属污染物、绝缘气隙及自由金属微粒等4种典型绝缘缺陷下的复合PD信息，提取出反映不同绝缘缺陷特征的PD统计特征量，并据此构建出一种适用于GIS设备PD识别的支持向量数据描述（Support Vector Data Description，简称SVDD）故障诊断方法。为此，本文所做的主要研究工作有：
①结合电磁波、天线辐射理论及光电子辐射原理，推导UHF信号能量与视在放电量的平方呈线性相关，荧光光纤信号的一次积分值与视在放电量之间的关联关系。通过实验，对不同气压SF6中UHF信号与视在放电量的关联关系做出修正，研究气压的影响特性及修正公式，并实测检验修正公式的有效性。同时，针对不同尺寸绝缘缺陷对PD光信号能量的影响，研究光信号能量受绝缘缺陷尺寸大小的影响特性与修正公式，并通过电场分析影响机理。实测检验荧光光纤检测法对微小绝缘缺陷引起的PD具有较高的灵敏度。
②结合脉冲电流法、UHF法和荧光光纤法，构建出用于检测GIS内部典型绝缘缺陷PD的联合检测系统。通过大量实验，获取了反映GIS典型绝缘缺陷特征的PD复合信息，构造出各类PD信号的φ-u-n三维谱图及φ-u、φ-n二维谱图，并提取出13个表征4种典型绝缘缺陷产生PD信息的统计特征量。在此基础上，采用核主成分分析方法，提取表征4种典型绝缘缺陷产生PD综合特点的特征子集TKPCA，并借鉴最大相关最小冗余算法对原始统计特征进行择优降维，结合能够表征PD源特征的视在放电量q、UHF信号能量E以及荧光光纤信号一次积分A，共同构造出辨识4种典型绝缘缺陷的最优特征子集TBEST。研究表明，该方法不仅有效保留了每类PD信号的特征，同时还显著降低了特征信息的冗余度。
③在PD类型识别中，引入SVDD方法，并借鉴支持向量机(support vectormachine，简SVM)最大化“间隔”思想，提出一种优化半径的OR-SVDD(OptimalRadius SVDD，简称OR-SVDD)方法来解决SVM辨识PD类型存在的漏分或错分问题，弥补了SVDD分类裕度不足的缺点，实现了多类缺陷的有效分类。
④针对SVM和SVDD算法中核函数参数σ与惩罚因子C的选择存在盲目性的问题，结合局部遗传算法和模拟退火算法对SVDD分类器中的核函数参数σ和惩罚因子C进行优化，解决了以往依靠经验设定参数的问题，使σ与C这两个对分类性能影响最大的参数的设置具有科学依据，并提升了算法分类性能和识别效率。
⑤针对实际故障诊断中存在的预定义故障重叠问题，使用主成分分析方法来优化Fisher判别分析（Fisher Discriminant Analysis，简称FDA），结合前文所构建的SVDD故障识别方法，提出一种使重叠的两类预定义故障在原始空间尽量分离后，再在Fisher投影空间实现最大分离的PF-SVDD方法。研究表明：该方法可将存在故障重叠情况时的60%低识别率提高到接近80%，显著增加了该诊断方法实用性。
Gas Insulated Substation (GIS) is widely used in urban power substation becauseof its advantages of small area coverage, operational reliability and low electromagneticpollution. However, due to some reasons in structure and transportation, there areinevitable insulation defects which may cause partial discharge in regular operation.The safe operation of grid is threatened seriously by insulation damage. Therefore, theon-line monitoring and fault type recognition in GIS has been the focus of research inthis field.
In this paper, statistical characteristics of different insulation defects PD signals arestudied based on analyzing researches about PD type recognition home and abroad.Methods to obtain different characteristic parameters are developed from differentangles of partial discharge pattern, Support Vector Data Description method is presentedfor PD type recognition in GIS. The main work and achievements are as follows.
①Large data of discharge experiment in different intensity is acquired by PDUHF monitoring system which has been developed for the detection of four kinds oftypical insulation defects model in the laboratory. The φ-u-n3D PD image and thecorresponding φ-u, φ-n two-dimensional image has been constructed.The results showthat: the differences of four PD image shape are rather obvious, the same type of PDimage shape remains unchanged in different voltage levels. Obtaining the13statisticalfeatures based on the two-dimensional image can lay a foundation for the research ofPD type recognition.
②Based on the electromagnetic theory, antenna and photoelectron radiationtheory, the relationship between apparent discharge quantity calculated by IEC60270and the detection signal could be obtained. Linear relationship between energy of UHFsignal and square of apparent discharge quantity has been found, while linearrelationship between the integral value of the signal of the optical method and thecharge quantity comes out. According to the practical situation, the correction formulaof gas pressure has been get by the research on the influence of different gas pressure toUHF signal and apparent discharge quantity. The effectiveness of optical method hasbeen also proved by experiment result.
③The KPCA method is presented for the extraction of feature subset of fourkinds of insulation defects discharge comprehensive characteristic. The Maximal Relevance Minimal Redundancy method is put forward for dimension reduction of theoriginal statistical characteristics. With apparent discharge quantity q, energy of UHFsignal E and optical energy A, two algorithms are combined to construct optimal featuresubset TBESTto identify four kinds of defects, which effectively retained thecharacteristics of each class of the PD signal and reduced the redundancy of statisticalcharacteristics.
④SVDD is introduced into PD type recognition, based on the principle ofMaximum interval of support vector machine and one to multiple of multipleclassification method, an optimal radius support vector data description algorithm(OR-SVDD) is proposed to solve the disadvantages of missing and wrong classificationin SVM and the lack of classification margin small in SVDD. The principle of“one-to-many” is adopted to solve the difficult problem of multi-class defectclassification, and to improve the identification ability and application value.
⑤As a result of optimization of classification performance, local GA algorithmand SA algorithm have been applied to optimize the kernel parameter σ and the penaltyfactor C of SVDD classifier. According to the real project, PCA-FDA has been proposed.Two overlapping classes of fault would desperate in original space, and then reach themaximum level in Fisher projection space. With the method, the low recognition ratio60%would rise high to80%to improve the applying value.
引文
[1]邱毓昌. GIS装置及其绝缘技术[M].水利电力出版社,1994.
[2]罗学琛.变电所使用GIS设备与常规设备的综合比较[J].中国电力,1996.4, Vol.29, No.4:24-26..
[3] Kopejtkova D, Molony T, Kobayashi S, et al. A twenty-five year review of experience withSF6gas insulated substations (GIS)[C]//INTERNATIONAL CONFERENCE ON LARGEHIGH VOLTAGE ELECTRIC SYSTEMS.1992,1:23-101.
[4] Istad M, Runde M. Thirty-six years of service experience with a national population ofgas-insulated substations[J]. IEEE Transactions on Power Delivery,2010,25(4):2448-2454
[5] CIGRE W G.33/23-12Insulation coordination of GIS: Return of experience, on site tests anddiagnostic techniques[J]. Electra,1998,176(2):67-95.
[6] Kranz H G. Fundamentals in computer aided PD processing, PD pattern recognition andautomated diagnosis in GIS[J]. IEEE Transactions on Dielectrics and Electrical Insulation,2000,7(1):12-20.
[7] Boggs S A. Partial discharge: overview and signal generation[J]. IEEE Electrical InsulationMagazine,1990,6(4):33-39.
[8]邱昌容,王乃庆等.电工设备局部放电及其测试技术[M].机械工业出版社,1994.
[9] Hasegawa Y, Izumi K, Kobayashi A, et al. Investigation on phenomena caused by insulationabnormalities in actual GIS[J]. IEEE Transactions on Power Delivery,1994,9(2):796-804.
[10]韩小莲. GIS局部放电检测系统的研究[D].西安交通大学出版社,1995.
[11]肖燕,郁惟镛. GIS中局部放电在线监测研究的现状与展望[J].高电压技术,2005,31(1):47-49.
[12]关根志.高电压工程基础[M].中国电力出版社,2003.
[13] Pryor B M. A review of partial discharge monitoring in gas insulated substations[A]. IEEColloquium Partial Discharges in Gas Insulated Substations[C], London,1994:1-2.
[14] M.D.Judd, O.Farish, B.F.Hampton. The Excitation of UHF Signals by Partial Discharges inGIS[J]. IEEE Transactions on Dielectrics and Electrical Insulation.1996,Vol.3No.2: pp.213-228.
[15]张晓星.组合电器局部放电非线性鉴别特征提取与模式识别方法研究[D].重庆重庆大学博士论文,2006.9.
[16]魏念荣,李航,段前伟,等.利用光纤技术监测高压电器设备局部放电的初步研究[J].内蒙古电力技术,2000,18(3):1-5.
[17]张晓星,姚尧,唐炬,等. SF6放电分解气体组分分析的现状和发展[J].高电压技术,2008,34(4):664-669.
[18]边肇祺,张学工.模式识别[M].清华大学出版社有限公司,2000.
[19]孙即祥,计算机图形学.现代模式识别[M].国防科技大学出版社,2002.
[20] Duda R O, Hart P E, Stork D G. Pattern classification[M]. Wiley-interscience,2012.
[21]唐铭.以复合复小波系数为特征量的局部放电模式识别研究[D].重庆大学硕士论文,2007.
[22]钱勇,黄成军,江秀臣,等.基于UHF法的GIS局部放电在线监测研究现状及展望[J].电网技术,2005,29(1):40-43.
[23]魏念荣,李航,段前伟,等.利用光纤技术监测高压电器设备局部放电的初步研究[J].内蒙古电力技术,2000,18(3):1-5.
[24]唐炬.组合电器局放在线监测外置传感器和复小波抑制干扰的研究.重庆大学博士学位论文,2004.5.
[25] L.E.Lundgarrd, M.Runde, B.Skyberg. Acoustic Diagnosis of Gas Insulated Substations: ATheoretical and Experimental Basis. IEEE Transactions on Dielectrics and ElectricalInsulation,1990, Vol.5, No.4: pp1751～1758.
[26]唐炬,朱伟等.检测GIS局部放电的超高频屏蔽谐振式环天线传感器研究[J].仪器仪表学报，2005,26(7):705~709.
[27]徐阳,曹晓珑等.局部放电光脉冲测量法与电测法的比较[J].高电压技术.2001，27(4)：3-5.
[28] Mangeret R, Farenc J, etal.Optical detection of partial discharge using fluorescent fiber[J].IEEE Trans on Electrical Insulation,1991,26(4):783-789.
[29]欧阳有鹏.电力设备局部放电荧光光纤传感系统的研制[D].重庆大学硕士学位论文，2011.9.
[30]王国利，郝艳棒，李彦明.光纤技术在电力变压器绝缘监测中的应用[J].高压电器，2001，37(2)：32-35.
[31] KATSUOSHI MUTO. Electric-Discharge Sensor Utilizing Fluorescent Optical Fiber[J].IEEE Journal of Light Wave Technology,1989,7(7):1029-1032.
[32] A.Beaoul, F.Buret. Optical Detector of Electrical Discharges [J]. IEE Proceedings-G,1991,138(5)：620-622.
[33] J.Farenc,R.Mangeret, A.Boulanger,et al.A fluorescent plastic optical fiber sensor for thedetecti-on of corona discharges in high voltage electrical equipment[J]. Rev. Sci.Instrum,1994,65(1):155-160
[34]郭灿新,张连宏,姚林朋,等.局部放电HF/UHF联合分析方法的现场电缆终端检测应用[J].电力自动化设备,2010,11(5):92-95.
[35]郑文栋,杨宁,钱勇,等.多传感器联合检测技术在XLPE电缆附件局部放电定位中的试验研究[J].电力系统保护与控制,2011,36(20):84-88.
[36]刘君华,姚明,黄成军,等.采用声电联合法的GIS局部放电定位试验研究[J].高电压技术,2009,33(10):2458-2463.R.Schwarz,M.Muhr,S.Pack.Partial discharge detection in oilwith optical methods[J]. IEEE Interna-tional Conference on Dielectric Liquids,2005.
[37] Reid, A.J., Judd, M.D., Fouracre. R.A. et al., Simultaneous measurement of partial dischargesusing IEC60270and radio-frequency techniques[J]. Dielectrics and Electrical Insulation,IEEE Transactions on,2011, Vol.18, No.2: pp:444-455.
[38]王颂.变压器局部放电超高频检测方法的标定研究[D].西安:西安交通大学,2007.
[39] S. Ohtsuka, T.Teshima, S. Matsumoto et al.,“Relationship between PD-inducedelectromagneti-c wave measured with UHF method and charge quantity obtained by PDcurrent waveform in model GIS”[J]2006IEEE Conference on Electrical Insulation andDielectric Phenomena (IEEE Cat No.06CH37829), pp.615-618,2006.9.
[40] Tang J, Liu F, Zhang X, et al. Partial discharge recognition through an analysis of SF6decomposition products part1: decomposition characteristics of SF6under four differentpartial discharges[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2012,Vol.19, No.1: pp:29-36.
[41] Fuping Z, Ju T, Xiaoxing Z. Influence of Trace Water and Oxygen on CharacteristicDecomposed Components of SF6under Partial Discharge[J]. International Conference onHigh Voltage Engineering and Application (ICHVE), Sept17-20,2012, Shang Hai, China:pp,505-508.
[42]唐炬,欧阳有鹏,范敏,等.用于检测变压器局部放电的荧光光纤传感系统研制[J].高电压技术,2011,37(5):1129-1135.
[43]赵晓辉,杨景刚等.油中局部放电检测脉冲电流法与超高频法比较.高电压技术，Vol.34,No.7, Jul.2007, pp.1401-1404.
[44] S. Ohtsuka, T. Teshima, S. Matsumoto et al.,“Relationship between PD-inducedelectromagnetic wave measured with UHF method and charge quantity obtained by PDcurrent waveform in model GIS,”2006IEEE Conference on Electrical Insulation andDielectric Phenomena (IEEE Cat No.06CH37829), pp.615-618,2006.
[45]王灿林，王柯，王黎明，等.基于紫外光脉冲检测技术的绝缘子电晕特性研究[J].电机工程学报，2007，27(36)：20-25
[46]汪金刚.高压设备放电紫外检测技术及其应用研究[D],重庆大学学位论文,2008.4
[47] Chang C, Chang C S, Jin J, et al. Source classification of partial discharge for gas insulatedsubstation using waveshape pattern recognition[J]. Dielectrics and Electrical Insulation, IEEETransactions on,2005,12(2):374-386.
[48] Chang C S, Jin J, Chang C, et al. Online source recognition of partial discharge for gasinsulated substations using independent component analysis[J]. Dielectrics and ElectricalInsulation, IEEE Transactions on,2006,13(4):892-902.
[49] Pinpart T, Fletcher J E, Judd M D. Methods for distinguishing between partial dischargesbased on the UHF detection technique[C]//Condition Monitoring and Diagnosis,2008. CMD2008. International Conference on. IEEE,2008:1060-1064.
[50]李立学,滕乐天,黄成军,等. GIS局部放电UHF信号的包络分析与缺陷识别[J].高电压技术,2009(2):260-265.
[51] Li J, Jiang T, Harrison R F, et al. Recognition of ultra high frequency partial discharge signalsusing multi-scale features[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2012,19(4):1412-1420.
[52] Xie Y, Tang J, Zhou Q. Feature extraction and recognition of UHF partial discharge signals inGIS based on dual‐tree complex wavelet transform[J]. European transactions on electricalpower,2010,20(5):639-649.
[53] Umamaheswari R, Sarathi R. Feature extraction of UHF PD signals by wavelet packet basedMRSD analysis For defect identification in Gas Insulated Systems[C]//India Conference(INDICON),2012Annual IEEE. IEEE,2012:1218-1222.
[54] Chang H C, Gu F C, Kuo C C. Applying Hilbert-Huang transform on partialdischarge patternrecognition of a gas insulated switchgear[C]//Power Modulator and High Voltage Conference(IPMHVC),2012IEEE International. IEEE,2012:165-168.
[55] Gulski E, Kreuger F H. Computer-aided recognition of discharge sources[J]. IEEETransactions on Electrical Insulation,1992,27(1):82-92.
[56] M.Cacciari, A.Contin, G.C.Montanar,Use of a Mixed-Weibull Distribution for theIdentification of PD Phenomena[J].IEEE Transaction on Dielectrics and ElectricalInsulation,1995,Vol.2,No.4, August.
[57] Contin A, Montanari G C, Ferraro C. PD source recognition by Weibull processing of pulseheight distributions[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2000,7(1):48-58.
[58]高凯,谈克雄,李福祺等.利用矩特征进行发电机线棒模型的局部放电模式识别[J].电工技术学报,2001.8, Vol.16, No.4:61-64.
[59] Gao K, Tan K, Li F, et al. PD pattern recognition for stator bar models with six kinds ofcharacteristic vectors using BP network[J]. Dielectrics and Electrical Insulation, IEEETransactions on,2002,9(3):381-389.
[60] Li J, Sun C, Grzybowski S, et al. Partial discharge image recognition using a new group offeatures[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2006,13(6):1245-1253.
[61]张晓星,唐炬,孙才新,等.基于多重分形维数的GIS局部放电模式识别[J].仪器仪表学报,2007,28(4):597-602.
[62] Lalitha E M, Satish L. Wavelet analysis for classification of multi-source PD patterns[J].Dielectrics and Electrical Insulation, IEEE Transactions on,2000,7(1):40-47.
[63]淡文刚.小波变换应用于大型电力变压器局部放电模式识别的研究.中国电力科学研究院博士学位论文,2000.9.
[64]唐炬,谢颜斌,周倩,等.基于最优小波包变换与核主分量分析的局部放电信号特征提取[J].电工技术学报,2010(9):35-40.
[65] Luukka P. Feature selection using fuzzy entropy measures with similarity classifier[J]. ExpertSystems with Applications,2011,38(4):4600-4607.
[66] Krivda. Automated Recognition of Partial Discharges[J].IEEE Trans.on Dielectrics andElectrical Insulation.Vol.2,No.5, Oct.1995.pp.796-821.
[67]袁曾任主编.人工神经网络及其应用[M].北京:清华大学出版社.南宁:广西科学技术出版社.1999年10月.
[68]刘丽兵,高乃奎,马小芹等. BP神经网络在大型发电机主绝缘击穿电压预测中的初步应用[J].电工电能新技术,2004,23(2):73-73.
[69]邱荣华,段志善,刘晓宁.模式识别在发电机局部放电检测系统中的应用[J].西北水力发电,2006,22(3):1-3.
[70]周天春,杨丽君,廖瑞金等.基于局部放电因子向量和BP神经网络的油纸绝缘老化状况诊断[J].电工技术学报,2010,25(10):18-23.
[71] L. Satish and W. S. Zaengl. Can Fractal Features be Used for Recognition3-D PartialDischarge Patterns. IEEE Transaction on Dielectrics and Electrical Insulation,1995, Vol.2,No.3: pp352-359.
[72] Kai Gao,Kexiong Tan,Fuqi Li. PD Pattern Recognition for Stator Bar Models with Six Kindsof Characteristic Vectors using BP Networks[J]. IEEE Transaction on Dielectrics andElectrical Insulation,2002, Vol.9, No.3: pp381～389
[73]王茹,林辉.用RBF网络进行电力变压器局部放电故障诊断[J].高压电器,2005,4(1).36-38
[74]韩小莲,冯允平.神经网络在气体绝缘组合电器局部放电诊断系统中的应用[J].高压电器,1995,31(4):43-45.
[75]唐炬,谢颜斌,周倩. GIS局部放电超高频信号复小波的模式识别[J].重庆大学学报(自然科学版),2009,32(9):1059-1064.
[76] Vapnik V N.The nature of statistical learning theory. Statistics for engineering andinformation science. Springer, Berlin,1999.
[77]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.
[78]王天健,吴振升,王晖等.基于最小二乘支持向量机的改进型GIS局部放电识别方法[J].电网技术,2011,35(11):178-182.
[79]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[80]司文荣,李军浩,袁鹏等.气体绝缘组合电器多局部放电源的检测与识别[J].中国电机工程学报,2009(16):119-126.
[81]孙林,杨世元.最小二乘支持向量机构造的函数链接型神经网络在滚动轴承故障诊断中的应用[J].中国电机工程学报,2010(8):82-87.
[82]贾嵘,张欣伟,徐其惠等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009,29(9):56-59.
[83] Tax D M J, Duin R P W. Support vector domain description[J]. Pattern recognition letters.1999,20(11):1191-1199.
[84]康守强,王玉静,杨广学等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):124-128.
[85] Sakla W, Chan A, Ji J, et al. An SVDD-based algorithm for target detection in hyperspectralimagery[J]. Geoscience and Remote Sensing Letters, IEEE,2011,8(2): pp384-388.
[86]刘永刚.局部放电光测法信号特征辨识及其与放电量的关系研究[D],重庆大学硕士学位论文,2012.6.
[87] Seo J, Ko H. Face detection using support vector domain description in color images[J].Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,2004, vol.5:pp729-732.
[88]陈利,蒋维东,杨礼.支持向量数据描述法在变压器故障预警中的应用[J].西南民族大学学报,2008,34(3):568-571.
[89]孙即祥,计算机图形学.现代模式识别[M].国防科技大学出版社,2002.
[90] Duda R O, Hart P E, Stork D G. Pattern classification[M]. Wiley-interscience,2012.
[91]李剑.局部放电模式识别特征提取与分形压缩方法的研究[D],重庆大学博士学位论文,2001.9.
[92] M.Cacciari, A.Contin, G.C.Montanar. Use of a Mixed-Weibull Distribution for theIdentification of PD Phenomena[J].IEEE Transaction on Dielectrics and Electrical Insulation,1995,Vol.2,No.6, Dec:pp1166-1179.
[93]林俊亦.组合电器局部放电统计特征优化与类型识别研究[D].重庆大学硕士论文,2013,6.
[94]以复合复小波系数为特征量的局部放电模式识别研究[D].重庆大学硕士论文,2007.
[95] Hans Gerd Kranz. Diagnosis of Partial Discharge Signals Using NeuralNetworks and Minim-um Distance Classification [J].IEEE Transaction on Electrical Insulation,1993,28(6).pp:1018-1024.
[96] Amira A.Mazroua.Discrimination Between PD Pulse Shapes Using Different Neural NetworkParadigms[J].IEEE Transaction on Electrical Insulation,1994,1(6):pp1119-1131.
[97]郑重,谈克雄,高凯.局部放电脉冲波形特征分析[J].高电压技术,1999,25(4):15-17.
[98] Tatsuki Okamoto， Naohiro Hozumi and Takahisa Imajo. Partial discharge PatternRecognition for Four kind of Electrical System[J]. IEEE Trans. On Electrical Insulation，1992(6):pp376-378.
[99]高凯,谈克雄,李福祺等.利用矩特征进行发电机线棒模型的局部放电模式识别[J].电工技术学报,2001,8(16):61-64.
[100]高凯，谈克雄，李福祺等.基于散点集分形特征的局部放电模式识别研究[J].中国电机工程学报,2002,5(22):22-26.
[101]胡明友,谢恒堏,蒋雄伟等.基于小波变换提取局部放电脉冲特征的影响因素分析[J],西安交通大学学报,1999,33(4):25-30.
[102]唐炬,谢颜斌,周倩等.基于最优小波包变换与核主分量分析的局部放电信号特征提取[J].电工技术学报,2010(9):35-40.
[103] R.J.Van Brunt. Physics and Chemistry of Partial Discharge and Corona-Recent Advancesand Future Challenges. IEEE Transactions on Dielectrics and Electrical Insulation,1994,6(5):pp761~783.
[104]李勇智,杨静宇.基于非负矩阵分解新的人脸识别方法[J].系统仿真学报,2008,20(1):111-116
[105]张晓星,唐炬,孙才新等.基于核统计不相关最优鉴别矢量集的GIS局部放电模式识别[J].电工技术学报,2008,23(9):111-117.
[106]吴诩,李永乐,胡庆军.应用数理统计[M].长沙：国防科技大学出版社,1995.
[107]廖瑞金,杨丽君,孙才新等.基于局部放电主成分因子向量的油纸绝缘老化状态统计分析[J].中国电机工程学报,2006,26(14):114-119
[108]唐炬,范敏等. SF6局部放电分解组分光声检测信号交叉响应处理技术[J].高电压技术,2013,39(2):257-264.
[109]王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005,27(12):68-71.
[110]毛勇,周晓波,夏铮等.特征选择算法研究综述[J].模式识别与人工智能,2007,20(2):211-218.
[111]刘华文.基于信息熵的特征选择算法研究[D].吉林大学博士论文,2010.5
[112]李兵,张培林,任国全等.基于互信息的滚动轴承故障特征选择方法[J].测试技术学报,2009,23(2):183-188
[113]王新峰,邱静,刘冠军.基于特征相关性和冗余性分析的机械故障特征选择研究[J].中国机械工程,2006,17(4):379-382.
[114]佘传伏,俞立钧,姚道敏.基于特征选择的支持向量机在故障诊断中的应用[J].现代机械,2007,1:22-24.
[115]周志红,周新聪,袁成清.基于过滤器-封装器组合模型的故障特征选择算法[J].中国机械工程,2007,18(16):1988-1991.
[116] Krivda. Automated Recognition of Partial Discharges[J].IEEE Trans.on Dielectrics andElectrical Insulation.Vol.2,No.5, Oct.1995.pp.796-821.
[117]袁曾任主编.人工神经网络及其应用[M].北京:清华大学出版社.南宁:广西科学技术出版社.1999年10月.
[118]刘丽兵,高乃奎,马小芹等. BP神经网络在大型发电机主绝缘击穿电压预测中的初步应用[J].电工电能新技术,2004,23(2):73-73.
[119]邱荣华,段志善,刘晓宁.模式识别在发电机局部放电检测系统中的应用[J].西北水力发电,2006,22(3):1-3.
[120]周天春,杨丽君,廖瑞金等.基于局部放电因子向量和BP神经网络的油纸绝缘老化状况诊断[J].电工技术学报,2010,25(10):18-23.
[121] L. Satish and W. S. Zaengl. Can Fractal Features be Used for Recognition3-D PartialDischarge Patterns. IEEE Transaction on Dielectrics and Electrical Insulation,1995, Vol.2,No.3: pp352-359.
[122] Kai Gao,Kexiong Tan,Fuqi Li. PD Pattern Recognition for Stator Bar Models with Six Kindsof Characteristic Vectors using BP Networks[J]. IEEE Transaction on Dielectrics andElectrical Insulation,2002, Vol.9, No.3: pp381～389
[123]王茹,林辉.用RBF网络进行电力变压器局部放电故障诊断[J].高压电器,2005,4(1).36-38
[124]韩小莲,冯允平.神经网络在气体绝缘组合电器局部放电诊断系统中的应用[J].高压电器,1995,31(4):43-45.
[125]唐炬,谢颜斌,周倩. GIS局部放电超高频信号复小波的模式识别[J].重庆大学学报(自然科学版),2009,32(9):1059-1064.
[126] Vapnik V N.The nature of statistical learning theory. Statistics for engineering andinformation science. Springer, Berlin,1999.
[127]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.
[128]王天健,吴振升,王晖等.基于最小二乘支持向量机的改进型GIS局部放电识别方法[J].电网技术,2011,35(11):178-182.
[129]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[130]司文荣,李军浩,袁鹏等.气体绝缘组合电器多局部放电源的检测与识别[J].中国电机工程学报,2009(16):119-126.
[131]孙林,杨世元.最小二乘支持向量机构造的函数链接型神经网络在滚动轴承故障诊断中的应用[J].中国电机工程学报,2010(8):82-87.
[132]贾嵘,张欣伟,徐其惠等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009,29(9):56-59.
[133] Tax D M J, Duin R P W. Support vector domain description[J]. Pattern recognition letters.1999,20(11):1191-1199.
[134]康守强,王玉静,杨广学等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):124-128.
[135] Sakla W, Chan A, Ji J, et al. An SVDD-based algorithm for target detection in hyperspectralimagery[J]. Geoscience and Remote Sensing Letters, IEEE,2011,8(2): pp384-388.
[136] Seo J, Ko H. Face detection using support vector domain description in color images[J].Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,2004, vol.5:pp729-732.
[137]陈利,蒋维东,杨礼.支持向量数据描述法在变压器故障预警中的应用[J].西南民族大学学报,2008,34(3):568-571.
[138]谢颜斌.超高频局部放电信号等效源数学模型及其与放电量的关联分析[D];重庆大学,2010.
[139]王少华,梅冰笑,叶自强,等.紫外成像检测技术及其在电气设备电晕放电检测中的应用[J].高压电器,2011,47(11):92-97.
[140]胡先志，胡佳妮.塑料光纤基础及应用[M].北京：人民邮电出版社，2010.
[141]雷玉堂.光电检测技术[M].北京：中国计量出版社，2009.
[142]孙才新，许高峰，唐炬等.以盒维数和信息维数为识别特征量的GIS局部放电模式识别[J].电机工程学报，,005，25(3)：100-104.
[143] Reid A J, Judd M D, Duncan G. Simultaneous Measurement of Partial Discharge Using TEV,IEC60270and UHF Techniques [J]. Conference Record of the2012IEEE InternationalSymposium on Electrical Insulation (ISEI),2012,439-442.
[144] Giussani R, Cotton I, Sloan R. Comparison of IEC60270and RF partial discharge detectionin an electromagnetic noise-free environment at differing pressures [J]. Conference Record ofthe2012IEEE International Symposium on Electrical Insulation (ISEI),2012,127-131.
[145] Reid A J, Judd M D, Fouracre R A, et al. Identification of simultaneously active partialdischarge sources using combined radio frequency and IEC60270measurement [J]. Science,Measurement&Technology, IET,2011,5(3):102-108.
[146] Reid A J, Judd M D, Fouracre R A, et al. Simultaneous measurement of partial dischargesusing IEC60270and radio-frequency techniques [J]. Dielectrics and Electrical Insulation,IEEE Transactions on,2011,18(2):444-455.
[147]吴建蓉.组合电器局部放电模式识别与放电量的高频信号校准研究[D];重庆大学,2011.
[148] Martin Hoof, Bernd Freisleben and Rainer Patsch. PD Source Identification with NovelDischarge Parameters using Counterpropagation Neural Networks.IEEE Transactions onDiele-ctrics and Electrical Insulation,Vol.4,No.1,Feb.1997:pp17~32.
[149]张中华，林殿新，于欣，等.光电子学原理与技术[M]．北京：北京航空航天大学出版社，2009．
[150]张占龙，王科，唐炬，等.变压器电晕放电紫外脉冲检测法[J].电力系统自动化，2010，34(2)：84-88.
[151]司文荣，李军浩，袁鹏，等．局部放电光测法的研究现状与发展[J]．高压电器，2008，44(3)：261-264.
[152] Farenc J，Mangeret R，Boulanger A，et al．A fluorescent plastic optical fiber sensor for thedetection of corona discharges in high voltage electrical equipment [J]．Review of ScientificInstruments,1994，65(1)：155-160.
[153]郑重,谈克雄,高凯.局部放电脉冲波形特征分析[J].高电压技术.1999,25(4):15~17.
[154] Masatake Kawada,Zen-Ichiro Kawasaki and Kenji Matsu-ura.A New on-line Insulation Diag-nostic Technique for Power Apparatus by Detecting Electromagnetic Signals Emitted frimPD[J].1996Asian International Conference on Dielectrics and Electrical Insulation,4thJapan-China Conference on Electrical Insulation Diagnosis, Xi'an,China, October,1996:pp325~328.
[155]葛景滂,邱昌容.局部放电测量[M].北京：机械工业出版社,1984
[156]杨钟瑾.核函数支持向量机[J].计算机工程与应用,2008,44(33):1-6.
[157]郑蕊蕊,赵继印,赵婷婷等.基于遗传支持向量机和灰色人工免疫算法的电力变压器故障诊断[J].中国电机工程学报,2011,31(7):56-63.
[158]罗苏南,赵希才,田朝勃等.用于气体绝缘开关的新型空心线圈电流互感器[J].电力系统自动化,2003(21)
[159]邢红杰，赵浩鑫.基于模拟退火的SVDD特征提取和参数选择[J].计算机科学,2013,40(1):302-305.
[160]徐图，何大可．超球体多类支持向量机理论[J].控制理论与应用,2009,26(11)：1293-1297
[161]唐明珠，王岳斌，阳春华.一种改进的支持向量数据描述故障诊断方法[J]．控制与决策,2011,26(7):967-972.
[162]赵峰，张军英，刘敬.一种改善支撑向量域描述性能的核优化算法[J].自动化学报，2008,34(9):1122-1127.
[163]蔡金燕，杜敏杰，孟亚峰等. SVDD参数优化的有限穷举_局部遗传算法及故障检测应用[J].微电子学与计算机,2013,30(2):21-25.
[164] Scott Kirkpatrick. Optimization by Simulated Annealing: Quantitative Studies[J]. Journal ofStatistical Physics,1984,VoL34:975-986.
[165]李来强，王树林，李生娟，等.基于模拟退火改进的神经网络算法在颗粒碰撞阻尼研究中的应用[J].震动与冲击，2010,29(3):89-90.
[166]章刚勇,阮陆宁.基于Monte Carlo随机模拟的几种正态性检验方法的比较[J].统计与决策,2011,7:17-20.
[167] Jasper. SVM入门[R/OL],2009, http://ishare.iask.sina.com.cn/f/6311061.html.
[168] Cristianini Nello, Shawe-Taylor John.支持向量机导论[M].北京:电子工业出版社.2004.27-35
[169]甘俊英,张有为.模式识别中广义核函数Fisher最佳鉴别[J].模式识别与人工智能,2002,15(4):429-434.
[170] Lee MMS, Keerthi SS, Ong CJ, et al. An efficient method for computing leave-one-out errorin support vector machine with Gaussian kernels[J]. IEEE Trans. Neural Networks,2004,15(3):750-757
[171] Zhang D, Chen S, Zhou H. Learning the kernel parameters in kernel minimum distanceclassifier[J]. Pattern Recognition,2006,39(1):133-135.
[172]蒋雄伟,王振华,谢恒堏.基于遗传算法的神经网络在局部放电模式识别中的应用.西安交通大学学报,1999, Vol.33, No.12: pp1～4
[173] D.Wenzel, H.Borsi, E.Gockenbach. A New Approach for Partial Discharge Recognition onTransformers on-site by means of Genetic Algorithms. Conference Record of the1996IEEEInternational Symposium on Electric Insulation, Montreal, Quebec, Canada,1996, June16-19:pp57～60
[174]邱毓昌.用超高频法对GIS绝缘进行在线监测.高压电器,1997,33(4):36～40.
[175]李天恩.基于混合算法的过程故障可拒绝模式分类方法研究[D].天津大学博士论文,2012.5
[2]罗学琛.变电所使用GIS设备与常规设备的综合比较[J].中国电力,1996.4, Vol.29, No.4:24-26..
[3] Kopejtkova D, Molony T, Kobayashi S, et al. A twenty-five year review of experience withSF6gas insulated substations (GIS)[C]//INTERNATIONAL CONFERENCE ON LARGEHIGH VOLTAGE ELECTRIC SYSTEMS.1992,1:23-101.
[4] Istad M, Runde M. Thirty-six years of service experience with a national population ofgas-insulated substations[J]. IEEE Transactions on Power Delivery,2010,25(4):2448-2454
[5] CIGRE W G.33/23-12Insulation coordination of GIS: Return of experience, on site tests anddiagnostic techniques[J]. Electra,1998,176(2):67-95.
[6] Kranz H G. Fundamentals in computer aided PD processing, PD pattern recognition andautomated diagnosis in GIS[J]. IEEE Transactions on Dielectrics and Electrical Insulation,2000,7(1):12-20.
[7] Boggs S A. Partial discharge: overview and signal generation[J]. IEEE Electrical InsulationMagazine,1990,6(4):33-39.
[8]邱昌容,王乃庆等.电工设备局部放电及其测试技术[M].机械工业出版社,1994.
[9] Hasegawa Y, Izumi K, Kobayashi A, et al. Investigation on phenomena caused by insulationabnormalities in actual GIS[J]. IEEE Transactions on Power Delivery,1994,9(2):796-804.
[10]韩小莲. GIS局部放电检测系统的研究[D].西安交通大学出版社,1995.
[11]肖燕,郁惟镛. GIS中局部放电在线监测研究的现状与展望[J].高电压技术,2005,31(1):47-49.
[12]关根志.高电压工程基础[M].中国电力出版社,2003.
[13] Pryor B M. A review of partial discharge monitoring in gas insulated substations[A]. IEEColloquium Partial Discharges in Gas Insulated Substations[C], London,1994:1-2.
[14] M.D.Judd, O.Farish, B.F.Hampton. The Excitation of UHF Signals by Partial Discharges inGIS[J]. IEEE Transactions on Dielectrics and Electrical Insulation.1996,Vol.3No.2: pp.213-228.
[15]张晓星.组合电器局部放电非线性鉴别特征提取与模式识别方法研究[D].重庆重庆大学博士论文,2006.9.
[16]魏念荣,李航,段前伟,等.利用光纤技术监测高压电器设备局部放电的初步研究[J].内蒙古电力技术,2000,18(3):1-5.
[17]张晓星,姚尧,唐炬,等. SF6放电分解气体组分分析的现状和发展[J].高电压技术,2008,34(4):664-669.
[18]边肇祺,张学工.模式识别[M].清华大学出版社有限公司,2000.
[19]孙即祥,计算机图形学.现代模式识别[M].国防科技大学出版社,2002.
[20] Duda R O, Hart P E, Stork D G. Pattern classification[M]. Wiley-interscience,2012.
[21]唐铭.以复合复小波系数为特征量的局部放电模式识别研究[D].重庆大学硕士论文,2007.
[22]钱勇,黄成军,江秀臣,等.基于UHF法的GIS局部放电在线监测研究现状及展望[J].电网技术,2005,29(1):40-43.
[23]魏念荣,李航,段前伟,等.利用光纤技术监测高压电器设备局部放电的初步研究[J].内蒙古电力技术,2000,18(3):1-5.
[24]唐炬.组合电器局放在线监测外置传感器和复小波抑制干扰的研究.重庆大学博士学位论文,2004.5.
[25] L.E.Lundgarrd, M.Runde, B.Skyberg. Acoustic Diagnosis of Gas Insulated Substations: ATheoretical and Experimental Basis. IEEE Transactions on Dielectrics and ElectricalInsulation,1990, Vol.5, No.4: pp1751～1758.
[26]唐炬,朱伟等.检测GIS局部放电的超高频屏蔽谐振式环天线传感器研究[J].仪器仪表学报，2005,26(7):705~709.
[27]徐阳,曹晓珑等.局部放电光脉冲测量法与电测法的比较[J].高电压技术.2001，27(4)：3-5.
[28] Mangeret R, Farenc J, etal.Optical detection of partial discharge using fluorescent fiber[J].IEEE Trans on Electrical Insulation,1991,26(4):783-789.
[29]欧阳有鹏.电力设备局部放电荧光光纤传感系统的研制[D].重庆大学硕士学位论文，2011.9.
[30]王国利，郝艳棒，李彦明.光纤技术在电力变压器绝缘监测中的应用[J].高压电器，2001，37(2)：32-35.
[31] KATSUOSHI MUTO. Electric-Discharge Sensor Utilizing Fluorescent Optical Fiber[J].IEEE Journal of Light Wave Technology,1989,7(7):1029-1032.
[32] A.Beaoul, F.Buret. Optical Detector of Electrical Discharges [J]. IEE Proceedings-G,1991,138(5)：620-622.
[33] J.Farenc,R.Mangeret, A.Boulanger,et al.A fluorescent plastic optical fiber sensor for thedetecti-on of corona discharges in high voltage electrical equipment[J]. Rev. Sci.Instrum,1994,65(1):155-160
[34]郭灿新,张连宏,姚林朋,等.局部放电HF/UHF联合分析方法的现场电缆终端检测应用[J].电力自动化设备,2010,11(5):92-95.
[35]郑文栋,杨宁,钱勇,等.多传感器联合检测技术在XLPE电缆附件局部放电定位中的试验研究[J].电力系统保护与控制,2011,36(20):84-88.
[36]刘君华,姚明,黄成军,等.采用声电联合法的GIS局部放电定位试验研究[J].高电压技术,2009,33(10):2458-2463.R.Schwarz,M.Muhr,S.Pack.Partial discharge detection in oilwith optical methods[J]. IEEE Interna-tional Conference on Dielectric Liquids,2005.
[37] Reid, A.J., Judd, M.D., Fouracre. R.A. et al., Simultaneous measurement of partial dischargesusing IEC60270and radio-frequency techniques[J]. Dielectrics and Electrical Insulation,IEEE Transactions on,2011, Vol.18, No.2: pp:444-455.
[38]王颂.变压器局部放电超高频检测方法的标定研究[D].西安:西安交通大学,2007.
[39] S. Ohtsuka, T.Teshima, S. Matsumoto et al.,“Relationship between PD-inducedelectromagneti-c wave measured with UHF method and charge quantity obtained by PDcurrent waveform in model GIS”[J]2006IEEE Conference on Electrical Insulation andDielectric Phenomena (IEEE Cat No.06CH37829), pp.615-618,2006.9.
[40] Tang J, Liu F, Zhang X, et al. Partial discharge recognition through an analysis of SF6decomposition products part1: decomposition characteristics of SF6under four differentpartial discharges[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2012,Vol.19, No.1: pp:29-36.
[41] Fuping Z, Ju T, Xiaoxing Z. Influence of Trace Water and Oxygen on CharacteristicDecomposed Components of SF6under Partial Discharge[J]. International Conference onHigh Voltage Engineering and Application (ICHVE), Sept17-20,2012, Shang Hai, China:pp,505-508.
[42]唐炬,欧阳有鹏,范敏,等.用于检测变压器局部放电的荧光光纤传感系统研制[J].高电压技术,2011,37(5):1129-1135.
[43]赵晓辉,杨景刚等.油中局部放电检测脉冲电流法与超高频法比较.高电压技术，Vol.34,No.7, Jul.2007, pp.1401-1404.
[44] S. Ohtsuka, T. Teshima, S. Matsumoto et al.,“Relationship between PD-inducedelectromagnetic wave measured with UHF method and charge quantity obtained by PDcurrent waveform in model GIS,”2006IEEE Conference on Electrical Insulation andDielectric Phenomena (IEEE Cat No.06CH37829), pp.615-618,2006.
[45]王灿林，王柯，王黎明，等.基于紫外光脉冲检测技术的绝缘子电晕特性研究[J].电机工程学报，2007，27(36)：20-25
[46]汪金刚.高压设备放电紫外检测技术及其应用研究[D],重庆大学学位论文,2008.4
[47] Chang C, Chang C S, Jin J, et al. Source classification of partial discharge for gas insulatedsubstation using waveshape pattern recognition[J]. Dielectrics and Electrical Insulation, IEEETransactions on,2005,12(2):374-386.
[48] Chang C S, Jin J, Chang C, et al. Online source recognition of partial discharge for gasinsulated substations using independent component analysis[J]. Dielectrics and ElectricalInsulation, IEEE Transactions on,2006,13(4):892-902.
[49] Pinpart T, Fletcher J E, Judd M D. Methods for distinguishing between partial dischargesbased on the UHF detection technique[C]//Condition Monitoring and Diagnosis,2008. CMD2008. International Conference on. IEEE,2008:1060-1064.
[50]李立学,滕乐天,黄成军,等. GIS局部放电UHF信号的包络分析与缺陷识别[J].高电压技术,2009(2):260-265.
[51] Li J, Jiang T, Harrison R F, et al. Recognition of ultra high frequency partial discharge signalsusing multi-scale features[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2012,19(4):1412-1420.
[52] Xie Y, Tang J, Zhou Q. Feature extraction and recognition of UHF partial discharge signals inGIS based on dual‐tree complex wavelet transform[J]. European transactions on electricalpower,2010,20(5):639-649.
[53] Umamaheswari R, Sarathi R. Feature extraction of UHF PD signals by wavelet packet basedMRSD analysis For defect identification in Gas Insulated Systems[C]//India Conference(INDICON),2012Annual IEEE. IEEE,2012:1218-1222.
[54] Chang H C, Gu F C, Kuo C C. Applying Hilbert-Huang transform on partialdischarge patternrecognition of a gas insulated switchgear[C]//Power Modulator and High Voltage Conference(IPMHVC),2012IEEE International. IEEE,2012:165-168.
[55] Gulski E, Kreuger F H. Computer-aided recognition of discharge sources[J]. IEEETransactions on Electrical Insulation,1992,27(1):82-92.
[56] M.Cacciari, A.Contin, G.C.Montanar,Use of a Mixed-Weibull Distribution for theIdentification of PD Phenomena[J].IEEE Transaction on Dielectrics and ElectricalInsulation,1995,Vol.2,No.4, August.
[57] Contin A, Montanari G C, Ferraro C. PD source recognition by Weibull processing of pulseheight distributions[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2000,7(1):48-58.
[58]高凯,谈克雄,李福祺等.利用矩特征进行发电机线棒模型的局部放电模式识别[J].电工技术学报,2001.8, Vol.16, No.4:61-64.
[59] Gao K, Tan K, Li F, et al. PD pattern recognition for stator bar models with six kinds ofcharacteristic vectors using BP network[J]. Dielectrics and Electrical Insulation, IEEETransactions on,2002,9(3):381-389.
[60] Li J, Sun C, Grzybowski S, et al. Partial discharge image recognition using a new group offeatures[J]. Dielectrics and Electrical Insulation, IEEE Transactions on,2006,13(6):1245-1253.
[61]张晓星,唐炬,孙才新,等.基于多重分形维数的GIS局部放电模式识别[J].仪器仪表学报,2007,28(4):597-602.
[62] Lalitha E M, Satish L. Wavelet analysis for classification of multi-source PD patterns[J].Dielectrics and Electrical Insulation, IEEE Transactions on,2000,7(1):40-47.
[63]淡文刚.小波变换应用于大型电力变压器局部放电模式识别的研究.中国电力科学研究院博士学位论文,2000.9.
[64]唐炬,谢颜斌,周倩,等.基于最优小波包变换与核主分量分析的局部放电信号特征提取[J].电工技术学报,2010(9):35-40.
[65] Luukka P. Feature selection using fuzzy entropy measures with similarity classifier[J]. ExpertSystems with Applications,2011,38(4):4600-4607.
[66] Krivda. Automated Recognition of Partial Discharges[J].IEEE Trans.on Dielectrics andElectrical Insulation.Vol.2,No.5, Oct.1995.pp.796-821.
[67]袁曾任主编.人工神经网络及其应用[M].北京:清华大学出版社.南宁:广西科学技术出版社.1999年10月.
[68]刘丽兵,高乃奎,马小芹等. BP神经网络在大型发电机主绝缘击穿电压预测中的初步应用[J].电工电能新技术,2004,23(2):73-73.
[69]邱荣华,段志善,刘晓宁.模式识别在发电机局部放电检测系统中的应用[J].西北水力发电,2006,22(3):1-3.
[70]周天春,杨丽君,廖瑞金等.基于局部放电因子向量和BP神经网络的油纸绝缘老化状况诊断[J].电工技术学报,2010,25(10):18-23.
[71] L. Satish and W. S. Zaengl. Can Fractal Features be Used for Recognition3-D PartialDischarge Patterns. IEEE Transaction on Dielectrics and Electrical Insulation,1995, Vol.2,No.3: pp352-359.
[72] Kai Gao,Kexiong Tan,Fuqi Li. PD Pattern Recognition for Stator Bar Models with Six Kindsof Characteristic Vectors using BP Networks[J]. IEEE Transaction on Dielectrics andElectrical Insulation,2002, Vol.9, No.3: pp381～389
[73]王茹,林辉.用RBF网络进行电力变压器局部放电故障诊断[J].高压电器,2005,4(1).36-38
[74]韩小莲,冯允平.神经网络在气体绝缘组合电器局部放电诊断系统中的应用[J].高压电器,1995,31(4):43-45.
[75]唐炬,谢颜斌,周倩. GIS局部放电超高频信号复小波的模式识别[J].重庆大学学报(自然科学版),2009,32(9):1059-1064.
[76] Vapnik V N.The nature of statistical learning theory. Statistics for engineering andinformation science. Springer, Berlin,1999.
[77]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.
[78]王天健,吴振升,王晖等.基于最小二乘支持向量机的改进型GIS局部放电识别方法[J].电网技术,2011,35(11):178-182.
[79]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[80]司文荣,李军浩,袁鹏等.气体绝缘组合电器多局部放电源的检测与识别[J].中国电机工程学报,2009(16):119-126.
[81]孙林,杨世元.最小二乘支持向量机构造的函数链接型神经网络在滚动轴承故障诊断中的应用[J].中国电机工程学报,2010(8):82-87.
[82]贾嵘,张欣伟,徐其惠等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009,29(9):56-59.
[83] Tax D M J, Duin R P W. Support vector domain description[J]. Pattern recognition letters.1999,20(11):1191-1199.
[84]康守强,王玉静,杨广学等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):124-128.
[85] Sakla W, Chan A, Ji J, et al. An SVDD-based algorithm for target detection in hyperspectralimagery[J]. Geoscience and Remote Sensing Letters, IEEE,2011,8(2): pp384-388.
[86]刘永刚.局部放电光测法信号特征辨识及其与放电量的关系研究[D],重庆大学硕士学位论文,2012.6.
[87] Seo J, Ko H. Face detection using support vector domain description in color images[J].Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,2004, vol.5:pp729-732.
[88]陈利,蒋维东,杨礼.支持向量数据描述法在变压器故障预警中的应用[J].西南民族大学学报,2008,34(3):568-571.
[89]孙即祥,计算机图形学.现代模式识别[M].国防科技大学出版社,2002.
[90] Duda R O, Hart P E, Stork D G. Pattern classification[M]. Wiley-interscience,2012.
[91]李剑.局部放电模式识别特征提取与分形压缩方法的研究[D],重庆大学博士学位论文,2001.9.
[92] M.Cacciari, A.Contin, G.C.Montanar. Use of a Mixed-Weibull Distribution for theIdentification of PD Phenomena[J].IEEE Transaction on Dielectrics and Electrical Insulation,1995,Vol.2,No.6, Dec:pp1166-1179.
[93]林俊亦.组合电器局部放电统计特征优化与类型识别研究[D].重庆大学硕士论文,2013,6.
[94]以复合复小波系数为特征量的局部放电模式识别研究[D].重庆大学硕士论文,2007.
[95] Hans Gerd Kranz. Diagnosis of Partial Discharge Signals Using NeuralNetworks and Minim-um Distance Classification [J].IEEE Transaction on Electrical Insulation,1993,28(6).pp:1018-1024.
[96] Amira A.Mazroua.Discrimination Between PD Pulse Shapes Using Different Neural NetworkParadigms[J].IEEE Transaction on Electrical Insulation,1994,1(6):pp1119-1131.
[97]郑重,谈克雄,高凯.局部放电脉冲波形特征分析[J].高电压技术,1999,25(4):15-17.
[98] Tatsuki Okamoto， Naohiro Hozumi and Takahisa Imajo. Partial discharge PatternRecognition for Four kind of Electrical System[J]. IEEE Trans. On Electrical Insulation，1992(6):pp376-378.
[99]高凯,谈克雄,李福祺等.利用矩特征进行发电机线棒模型的局部放电模式识别[J].电工技术学报,2001,8(16):61-64.
[100]高凯，谈克雄，李福祺等.基于散点集分形特征的局部放电模式识别研究[J].中国电机工程学报,2002,5(22):22-26.
[101]胡明友,谢恒堏,蒋雄伟等.基于小波变换提取局部放电脉冲特征的影响因素分析[J],西安交通大学学报,1999,33(4):25-30.
[102]唐炬,谢颜斌,周倩等.基于最优小波包变换与核主分量分析的局部放电信号特征提取[J].电工技术学报,2010(9):35-40.
[103] R.J.Van Brunt. Physics and Chemistry of Partial Discharge and Corona-Recent Advancesand Future Challenges. IEEE Transactions on Dielectrics and Electrical Insulation,1994,6(5):pp761~783.
[104]李勇智,杨静宇.基于非负矩阵分解新的人脸识别方法[J].系统仿真学报,2008,20(1):111-116
[105]张晓星,唐炬,孙才新等.基于核统计不相关最优鉴别矢量集的GIS局部放电模式识别[J].电工技术学报,2008,23(9):111-117.
[106]吴诩,李永乐,胡庆军.应用数理统计[M].长沙：国防科技大学出版社,1995.
[107]廖瑞金,杨丽君,孙才新等.基于局部放电主成分因子向量的油纸绝缘老化状态统计分析[J].中国电机工程学报,2006,26(14):114-119
[108]唐炬,范敏等. SF6局部放电分解组分光声检测信号交叉响应处理技术[J].高电压技术,2013,39(2):257-264.
[109]王娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005,27(12):68-71.
[110]毛勇,周晓波,夏铮等.特征选择算法研究综述[J].模式识别与人工智能,2007,20(2):211-218.
[111]刘华文.基于信息熵的特征选择算法研究[D].吉林大学博士论文,2010.5
[112]李兵,张培林,任国全等.基于互信息的滚动轴承故障特征选择方法[J].测试技术学报,2009,23(2):183-188
[113]王新峰,邱静,刘冠军.基于特征相关性和冗余性分析的机械故障特征选择研究[J].中国机械工程,2006,17(4):379-382.
[114]佘传伏,俞立钧,姚道敏.基于特征选择的支持向量机在故障诊断中的应用[J].现代机械,2007,1:22-24.
[115]周志红,周新聪,袁成清.基于过滤器-封装器组合模型的故障特征选择算法[J].中国机械工程,2007,18(16):1988-1991.
[116] Krivda. Automated Recognition of Partial Discharges[J].IEEE Trans.on Dielectrics andElectrical Insulation.Vol.2,No.5, Oct.1995.pp.796-821.
[117]袁曾任主编.人工神经网络及其应用[M].北京:清华大学出版社.南宁:广西科学技术出版社.1999年10月.
[118]刘丽兵,高乃奎,马小芹等. BP神经网络在大型发电机主绝缘击穿电压预测中的初步应用[J].电工电能新技术,2004,23(2):73-73.
[119]邱荣华,段志善,刘晓宁.模式识别在发电机局部放电检测系统中的应用[J].西北水力发电,2006,22(3):1-3.
[120]周天春,杨丽君,廖瑞金等.基于局部放电因子向量和BP神经网络的油纸绝缘老化状况诊断[J].电工技术学报,2010,25(10):18-23.
[121] L. Satish and W. S. Zaengl. Can Fractal Features be Used for Recognition3-D PartialDischarge Patterns. IEEE Transaction on Dielectrics and Electrical Insulation,1995, Vol.2,No.3: pp352-359.
[122] Kai Gao,Kexiong Tan,Fuqi Li. PD Pattern Recognition for Stator Bar Models with Six Kindsof Characteristic Vectors using BP Networks[J]. IEEE Transaction on Dielectrics andElectrical Insulation,2002, Vol.9, No.3: pp381～389
[123]王茹,林辉.用RBF网络进行电力变压器局部放电故障诊断[J].高压电器,2005,4(1).36-38
[124]韩小莲,冯允平.神经网络在气体绝缘组合电器局部放电诊断系统中的应用[J].高压电器,1995,31(4):43-45.
[125]唐炬,谢颜斌,周倩. GIS局部放电超高频信号复小波的模式识别[J].重庆大学学报(自然科学版),2009,32(9):1059-1064.
[126] Vapnik V N.The nature of statistical learning theory. Statistics for engineering andinformation science. Springer, Berlin,1999.
[127]弓艳朋,刘有为,吴立远.采用分形和支持向量机的气体绝缘组合电器局部放电类型识别[J].电网技术,2011,35(3):135-139.
[128]王天健,吴振升,王晖等.基于最小二乘支持向量机的改进型GIS局部放电识别方法[J].电网技术,2011,35(11):178-182.
[129]赵文清,朱永利,张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报,2008,28(25):14-19.
[130]司文荣,李军浩,袁鹏等.气体绝缘组合电器多局部放电源的检测与识别[J].中国电机工程学报,2009(16):119-126.
[131]孙林,杨世元.最小二乘支持向量机构造的函数链接型神经网络在滚动轴承故障诊断中的应用[J].中国电机工程学报,2010(8):82-87.
[132]贾嵘,张欣伟,徐其惠等.基于LS-SVM回归的频域分析法及其在局放窄带干扰抑制中应用[J].电力自动化设备,2009,29(9):56-59.
[133] Tax D M J, Duin R P W. Support vector domain description[J]. Pattern recognition letters.1999,20(11):1191-1199.
[134]康守强,王玉静,杨广学等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):124-128.
[135] Sakla W, Chan A, Ji J, et al. An SVDD-based algorithm for target detection in hyperspectralimagery[J]. Geoscience and Remote Sensing Letters, IEEE,2011,8(2): pp384-388.
[136] Seo J, Ko H. Face detection using support vector domain description in color images[J].Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,2004, vol.5:pp729-732.
[137]陈利,蒋维东,杨礼.支持向量数据描述法在变压器故障预警中的应用[J].西南民族大学学报,2008,34(3):568-571.
[138]谢颜斌.超高频局部放电信号等效源数学模型及其与放电量的关联分析[D];重庆大学,2010.
[139]王少华,梅冰笑,叶自强,等.紫外成像检测技术及其在电气设备电晕放电检测中的应用[J].高压电器,2011,47(11):92-97.
[140]胡先志，胡佳妮.塑料光纤基础及应用[M].北京：人民邮电出版社，2010.
[141]雷玉堂.光电检测技术[M].北京：中国计量出版社，2009.
[142]孙才新，许高峰，唐炬等.以盒维数和信息维数为识别特征量的GIS局部放电模式识别[J].电机工程学报，,005，25(3)：100-104.
[143] Reid A J, Judd M D, Duncan G. Simultaneous Measurement of Partial Discharge Using TEV,IEC60270and UHF Techniques [J]. Conference Record of the2012IEEE InternationalSymposium on Electrical Insulation (ISEI),2012,439-442.
[144] Giussani R, Cotton I, Sloan R. Comparison of IEC60270and RF partial discharge detectionin an electromagnetic noise-free environment at differing pressures [J]. Conference Record ofthe2012IEEE International Symposium on Electrical Insulation (ISEI),2012,127-131.
[145] Reid A J, Judd M D, Fouracre R A, et al. Identification of simultaneously active partialdischarge sources using combined radio frequency and IEC60270measurement [J]. Science,Measurement&Technology, IET,2011,5(3):102-108.
[146] Reid A J, Judd M D, Fouracre R A, et al. Simultaneous measurement of partial dischargesusing IEC60270and radio-frequency techniques [J]. Dielectrics and Electrical Insulation,IEEE Transactions on,2011,18(2):444-455.
[147]吴建蓉.组合电器局部放电模式识别与放电量的高频信号校准研究[D];重庆大学,2011.
[148] Martin Hoof, Bernd Freisleben and Rainer Patsch. PD Source Identification with NovelDischarge Parameters using Counterpropagation Neural Networks.IEEE Transactions onDiele-ctrics and Electrical Insulation,Vol.4,No.1,Feb.1997:pp17~32.
[149]张中华，林殿新，于欣，等.光电子学原理与技术[M]．北京：北京航空航天大学出版社，2009．
[150]张占龙，王科，唐炬，等.变压器电晕放电紫外脉冲检测法[J].电力系统自动化，2010，34(2)：84-88.
[151]司文荣，李军浩，袁鹏，等．局部放电光测法的研究现状与发展[J]．高压电器，2008，44(3)：261-264.
[152] Farenc J，Mangeret R，Boulanger A，et al．A fluorescent plastic optical fiber sensor for thedetection of corona discharges in high voltage electrical equipment [J]．Review of ScientificInstruments,1994，65(1)：155-160.
[153]郑重,谈克雄,高凯.局部放电脉冲波形特征分析[J].高电压技术.1999,25(4):15~17.
[154] Masatake Kawada,Zen-Ichiro Kawasaki and Kenji Matsu-ura.A New on-line Insulation Diag-nostic Technique for Power Apparatus by Detecting Electromagnetic Signals Emitted frimPD[J].1996Asian International Conference on Dielectrics and Electrical Insulation,4thJapan-China Conference on Electrical Insulation Diagnosis, Xi'an,China, October,1996:pp325~328.
[155]葛景滂,邱昌容.局部放电测量[M].北京：机械工业出版社,1984
[156]杨钟瑾.核函数支持向量机[J].计算机工程与应用,2008,44(33):1-6.
[157]郑蕊蕊,赵继印,赵婷婷等.基于遗传支持向量机和灰色人工免疫算法的电力变压器故障诊断[J].中国电机工程学报,2011,31(7):56-63.
[158]罗苏南,赵希才,田朝勃等.用于气体绝缘开关的新型空心线圈电流互感器[J].电力系统自动化,2003(21)
[159]邢红杰，赵浩鑫.基于模拟退火的SVDD特征提取和参数选择[J].计算机科学,2013,40(1):302-305.
[160]徐图，何大可．超球体多类支持向量机理论[J].控制理论与应用,2009,26(11)：1293-1297
[161]唐明珠，王岳斌，阳春华.一种改进的支持向量数据描述故障诊断方法[J]．控制与决策,2011,26(7):967-972.
[162]赵峰，张军英，刘敬.一种改善支撑向量域描述性能的核优化算法[J].自动化学报，2008,34(9):1122-1127.
[163]蔡金燕，杜敏杰，孟亚峰等. SVDD参数优化的有限穷举_局部遗传算法及故障检测应用[J].微电子学与计算机,2013,30(2):21-25.
[164] Scott Kirkpatrick. Optimization by Simulated Annealing: Quantitative Studies[J]. Journal ofStatistical Physics,1984,VoL34:975-986.
[165]李来强，王树林，李生娟，等.基于模拟退火改进的神经网络算法在颗粒碰撞阻尼研究中的应用[J].震动与冲击，2010,29(3):89-90.
[166]章刚勇,阮陆宁.基于Monte Carlo随机模拟的几种正态性检验方法的比较[J].统计与决策,2011,7:17-20.
[167] Jasper. SVM入门[R/OL],2009, http://ishare.iask.sina.com.cn/f/6311061.html.
[168] Cristianini Nello, Shawe-Taylor John.支持向量机导论[M].北京:电子工业出版社.2004.27-35
[169]甘俊英,张有为.模式识别中广义核函数Fisher最佳鉴别[J].模式识别与人工智能,2002,15(4):429-434.
[170] Lee MMS, Keerthi SS, Ong CJ, et al. An efficient method for computing leave-one-out errorin support vector machine with Gaussian kernels[J]. IEEE Trans. Neural Networks,2004,15(3):750-757
[171] Zhang D, Chen S, Zhou H. Learning the kernel parameters in kernel minimum distanceclassifier[J]. Pattern Recognition,2006,39(1):133-135.
[172]蒋雄伟,王振华,谢恒堏.基于遗传算法的神经网络在局部放电模式识别中的应用.西安交通大学学报,1999, Vol.33, No.12: pp1～4
[173] D.Wenzel, H.Borsi, E.Gockenbach. A New Approach for Partial Discharge Recognition onTransformers on-site by means of Genetic Algorithms. Conference Record of the1996IEEEInternational Symposium on Electric Insulation, Montreal, Quebec, Canada,1996, June16-19:pp57～60
[174]邱毓昌.用超高频法对GIS绝缘进行在线监测.高压电器,1997,33(4):36～40.
[175]李天恩.基于混合算法的过程故障可拒绝模式分类方法研究[D].天津大学博士论文,2012.5